© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15981
    Prev
    Next
    INDEX
    Explanations

    programming constructs and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åįģéĩĮ
    -0.07
    ä¸ĩå²ģ
    -0.07
    åĬĽå£«
    -0.06
    èįŁ
    -0.06
    wu
    -0.06
    éħ
    -0.06
    yage
    -0.06
    egas
    -0.06
    INK
    -0.06
    ç´ł
    -0.06
    POSITIVE LOGITS
    åİ»ä½ķ
    0.08
    ForObject
    0.08
    elaar
    0.08
    ׳×ĵ
    0.08
    ares
    0.07
    cind
    0.07
    ignano
    0.07
    åıĪä¸į
    0.07
    没éĤ£ä¹Ī
    0.07
    ObjectContext
    0.07
    Activations Density 0.033%

    No Known Activations